> Suggest community skills based on recent activity in other plugins. Checks whether the community has built something relevant to a task and mentions it once, non-intrusively. Use when the user says "is there a community skill for this", "what else is out there", or asks for skill recommendations; also runs passively as part of other plugins' workflows.
npx skills add https://github.com/anthropics/claude-for-legal --skill related-skills-surfacer
~/.claude/plugins/config/claude-for-legal/legal-builder-hub/CLAUDE.md → practice profile.The community might have built the thing you're about to build. This skill notices and mentions it — once, briefly, non-annoyingly.
This skill surfaces related community skills after a task. It can be invoked directly by the user ("what else is out there for X?") or wired into other plugins via a Stop hook — the hook-based pattern requires each sibling plugin to declare a Stop hook that calls this skill, which is not wired by default. Without the hook wiring, invoke it directly.
Other plugins can include a light check at the end of a task:
> "The legal-builder-hub found a community skill that might help with this kind of thing: [name] — [one-line]. Want to take a look?"
~/.claude/plugins/config/claude-for-legal/legal-builder-hub/CLAUDE.md → practice profile, installed skills (don't suggest what's already installed).
Registry cache from registry-browser.
Given a task description (what the user was just doing), find registry skills that match:
Threshold: Only surface if the match is strong. Weak matches are noise. Better to surface nothing than to annoy.
If strong match:
> 💡 The community has a skill for this: [name] from [registry] — "[description]". /legal-builder-hub:skill-installer [name] to try it.
If no strong match: silent. No output. Don't announce "I found nothing."
Don't surface the same skill twice. If the user didn't install it the first time, they saw it and decided no. Track dismissals in references/surfaced.json.
Per ~/.claude/plugins/config/claude-for-legal/legal-builder-hub/CLAUDE.md → new skill notifications:
End with the next-steps decision tree per CLAUDE.md ## Outputs. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Replace with description of the skill and when Claude should use it.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when executing implementation plans with independent tasks in the current session
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Take anthropics/related-skills-surfacer from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.